Frontier AI Evaluation Engineer

Artificial Intelligence Underwriting Company; San Francisco (CA); On-site; USD 130,000 - 190,000; Full time

Benefits offered by this job

Equity

Health insurance

Visa sponsorship & relocation to SF

Daily lunch

Job summary

Artificial Intelligence Underwriting Company in San Francisco seeks an engineer to own customer integrations and evaluations end-to-end. You will read API docs, chase credentials, and wire customer agents into our evaluation system.

You will directly manage customer relationships, deliver results with technical detail, and decide if agents meet the AIUC-1 standard. You’ll collaborate across Delivery, core engineering, sales, and the Standards team.

Qualifications

• 3-7 years of experience in an early engineering role owning customers or in integration/solutions roles.
• Enough software engineering to build and debug integrations and decide when a scrappy version suffices.
• Comfort owning a customer relationship – scoping work, setting expectations, delivering hard news when needed.
• Customer obsession: the problem is your problem and you see it through.
• The discipline to turn field learnings into reusable solutions.

Responsibilities

• Own the path from signed customer to delivered results, scoping tests, validating authentic interfaces, and getting the agent running in our system.
• Build the one-off version when a customer doesn’t fit the product yet, and make it work.
• Deliver results directly to the customer and be the trusted technical contact.
• Decide whether a customer meets the AIUC-1 standard.
• Collaborate across Delivery, core engineers, sales, Standards, and the customer’s engineering team.
• Turn field learnings into product improvements.

Skills

Software engineering

Customer relationship

API integrations

Startup experience

Job description

Artificial Intelligence Underwriting Company in San Francisco seeks an engineer to own customer integrations and evaluations end-to-end. You will read API docs, chase credentials, and wire customer agents into our evaluation system.

You will directly manage customer relationships, deliver results with technical detail, and decide if agents meet the AIUC-1 standard. You’ll collaborate across Delivery, core engineering, sales, and the Standards team.